mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
9472945299
- pass a PIL.Image to img2img and inpaint rather than tensor - To support clipseg, inpaint needs to accept an "L" or "1" format mask. Made the appropriate change. |
||
---|---|---|
.. | ||
data | ||
invoke | ||
models | ||
modules | ||
generate.py | ||
lr_scheduler.py | ||
simplet2i.py | ||
util.py |